© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50184
    Prev
    Next
    INDEX
    Explanations

    fusion bonding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecto
    -0.06
    ùy
    -0.06
     Requests
    -0.06
    вл
    -0.06
    ãĤĤãģ¨
    -0.06
    åı±
    -0.05
    _LS
    -0.05
    alker
    -0.05
    ke
    -0.05
    å´Ľèµ·
    -0.05
    POSITIVE LOGITS
    gara
    0.08
    ussi
    0.07
    راÙĭ
    0.07
    gba
    0.07
    utr
    0.06
    æĢ§åħ³èĬĤçĤİ
    0.06
     posit
    0.06
    .nc
    0.06
    bigint
    0.06
    /linux
    0.06
    Activations Density 1.263%

    No Known Activations